Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Model risks

Deception and scheming9Reward hacking11Misalignment and value divergence3Dangerous agent actions20Dangerous capabilities8Inappropriate refusal3

System type

Models and APIs0AI Agent7coding agent1Embodied systems and robotics2

Layer

Prompt layer5Model layer45Application layer3Training and data layer13
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Model risks：Inappropriate refusalSystem type：Models and APIsSystem type：coding agentSystem type：Embodied systems and roboticsLayer：Application layerClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2605.19722

    研究用 30 项漏洞分析任务评测自主安全智能体的安全对齐效果

    评测自主安全智能体在授权漏洞分析中的对齐拒答效应

    arXiv
    2605.19722
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Gemma 4 31B official instruction-tuned model, TrevorJS Gemma 4 31B uncensored GGUF, Gemma 4 26B A4B official instruction-tuned model and others8
    Abstract轨迹级评测把拒答、接地、工具接口分开。

    这项工作把安全对齐效应测成自主安全智能体的轨迹属性，而不是单轮拒答率。

    Paper analysisRead analysis
You have reached the end